检索结果-内蒙古大学图书馆

MAT: A multimodal attentive translator for image captioning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Liu, Chang Sun, Fuchun Wang, Changhu Wang, Feng Yuille, Alan Department of Computer Science Tsinghua University China Toutiao AI Lab Department of Electronic Engineering UESTC China Cognitive Science & Computer Science Johns Hopkins University United States

In this work we formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different from most existing work where the whole image is represented by convolutional neural network (CNN) feature, we propose to represent the input image as a sequence of detected objects which feeds as the source sequence of the RNN model. In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model. To represent the image in a sequential way, we extract the objects features in the image and arrange them in a order using convolutional neural networks. To further leverage the visual information from the encoded objects, a sequential attention layer is introduced to selectively attend to the objects that are related to generate corresponding words in the sentences. Extensive experiments are conducted to validate the proposed approach on popular benchmark dataset, i.e., MS COCO, and the proposed model surpasses the state-of-the-art methods in all metrics following the dataset splits of previous work. The proposed approach is also evaluated by the evaluation server of MS COCO captioning challenge, and achieves very competitive results, e.g., a CIDEr of 1.029 (c5) and 1.064 (c40). Copyright © 2017, The Authors. All rights reserved.

关键词： Object detection

Fast Characterization of Segmental Duplications in Genome Assemblies

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Numanagić, Ibrahim Gökkaya, Alim S. Zhang, Lillian Berger, Bonnie Alkan, Can Hach, Faraz Computer Science and AI Lab Massachusetts Institute of Technology CambridgeMA02139 United States Department of Mathematics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Computer Engineering Bilkent University Ankara06800 Turkey Vancouver Prostate Centre VancouverV6H 3Z9 Canada Department of Urologic Sciences University of British Columbia VancouverV5Z 1M9 Canada

Motivation: Segmental duplications (SDs), or low-copy repeats (LCR), are segments of DNA greater than 1 Kbp with high sequence identity that are copied to other regions of the genome. SDs are among the most important sources of evolution, a common cause of genomic structural variation, and several are associated with diseases of genomic origin including schizophrenia and autism. Despite their functional importance, SDs present one of the major hurdles for de novo genome assembly due to the ambiguity they cause in building and traversing both state-of-the-art overlap-layout-consensus and de Bruijn graphs. This causes SD regions to be misassembled, collapsed into a unique representation, or completely missing from assembled reference genomes for various organisms. In turn, this missing or incorrect information limits our ability to fully understand the evolution and the architecture of the genomes. Despite the essential need to accurately characterize SDs in assemblies, there is only one tool that has been developed for this purpose, called Whole Genome Assembly Comparison (WGAC);its primary goal is SD detection. WGAC is comprised of several steps that employ different tools and custom scripts, which makes this strategy difficult and time consuming to use. Thus there is still a need for algorithms to characterize within-assembly SDs quickly, accurately, and in a user friendly manner. Results: Here we introduce SEgmental Duplication Evaluation Framework (SEDEF) to rapidly detect SDs through sophisticated filtering strategies based on Jaccard similarity and local chaining. We show that SEDEF accurately detects SDs while maintaining substantial speed up over WGAC that translates into practical run times of minutes instead of weeks. Notably, our algorithm captures up to 25% "pairwise error" between segments, whereas previous studies focused on only 10%, allowing us to more deeply track the evolutionary history of the genome. Availability: SEDEF is available at https://git

关键词： Diseases

Correction to: The role of machine learning in clinical research: transforming the future of evidence generation

学校读者我要写书评

暂无评论

Trials 2021年第1期22卷 593页

作者： E Hope Weissler Tristan Naumann Tomas Andersson Rajesh Ranganath Olivier Elemento Yuan Luo Daniel F Freitag James Benoit Michael C Hughes Faisal Khan Paul Slater Khader Shameer Matthew Roe Emmette Hutchison Scott H Kollins Uli Broedl Zhaoling Meng Jennifer L Wong Lesley Curtis Erich Huang Marzyeh Ghassemi Duke Clinical Research Institute Duke University School of Medicine Box 2834 Durham NC 27701 USA. Hope.weissler@duke.edu. Microsoft Research Cambridge MA USA. AstraZeneca Gothenburg Sweden. Courant Institute of Mathematical Science New York University New York NY USA. Englander Institute for Precision Medicine Weill Cornell Medical College New York NY USA. Northwestern University Clinical and Translational Sciences Institute Northwestern University Chicago IL USA. Division Pharmaceuticals Open Innovation and Digital Technologies Bayer AG Wuppertal Germany. University of Alberta Edmonton Alberta Canada. Department of Computer Science Tufts University Medford MA USA. Billion Minds Inc. Seattle WA USA. Verana Health San Francisco CA USA. Duke Clinical Research Institute Duke University School of Medicine Box 2834 Durham NC 27701 USA. Boehringer-Ingelheim Burlington Canada. Sanofi Cambridge MA USA. Sanofi Washington DC USA. Duke Forge Durham NC USA. Vector Institute University of Toronto Toronto Ontario Canada. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA. Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA. CIFAR AI Chair Vector Institute Toronto Ontario Canada.

Adversarially regularized autoencoders

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhao, Jake Kim, Yoon Zhang, Kelly Rush, Alexander M. LeCun, Yann Department of Computer Science New York University Facebook AI Research School of Engineering and Applied Sciences Harvard University

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures, such as text sequences or discretized images, has proven to be more challenging. In this work, we propose a flexible method for training deep latent variable models of discrete structures. Our approach is based on the recently-proposed Wasserstein autoencoder (WAE) which formalizes the adversarial autoencoder (AAE) as an optimal transport problem. We first extend this framework to model discrete sequences, and then further explore different learned priors targeting a controllable representation. This adversarially regularized autoencoder (ARAE) allows us to generate natural textual outputs as well as perform manipulations in the latent space to induce change in the output space. Finally we show that the latent representation can be trained to perform unaligned textual style transfer, giving improvements both in automatic/human evaluation compared to existing methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

Likelihood-free inference with emulator networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Lueckmann, Jan-Matthis Bassetto, Giacomo Karaletsos, Theofanis Macke, Jakob H. Computational Neuroengineering Department of Electrical and Computer Engineering Technical University of Munich Germany Neural Systems Analysis Research Center Max Planck Society Bonn Germany Uber AI Labs Uber Technologies Inc. San FranciscoCA United States Centre for Cognitive Science Technische Universität Darmstadt Germany

Approximate Bayesian Computation (ABC) provides methods for Bayesian inference in simulation-based models which do not permit tractable likelihoods. We present a new ABC method which uses probabilistic neural emulator networks to learn synthetic likelihoods on simulated data - both 'local' emulators which approximate the likelihood for specific observed data, as well as 'global' ones which are applicable to a range of data. Simulations are chosen adaptively using an acquisition function which takes into account uncertainty about either the posterior distribution of interest, or the parameters of the emulator. Our approach does not rely on user-defined rejection thresholds or distance functions. We illustrate inference with emulator networks on synthetic examples and on a biophysical neuron model, and show that emulators allow accurate and efficient inference even on problems which are challenging for conventional ABC approaches. Copyright © 2018, The Authors. All rights reserved.

关键词： Bayesian networks

Bayesian deep learning for exoplanet atmospheric retrieval

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Soboczenski, Frank Himes, Michael D. O'Beirne, Molly D. Zorzan, Simone Baydin, Atılım Güneş Cobb, Adam D. Gal, Yarin Angerhausen, Daniel Mascaro, Massimo Arney, Giada N. Domagal-Goldman, Shawn D. School of Population Health and Environmental Sciences King's College London Planetary Sciences Group Department of Physics University of Central Florida Department of Geology and Environmental Science University of Pittsburgh ERIN Department Luxembourg Institute of Science and Technology Department of Engineering Science University of Oxford Department of Computer Science University of Oxford Center for Space and Habitability University of Bern OCTO Applied AI Google Cloud Virtual Planetary Laboratory Team NASA Astrobiology Institute Planetary Systems Laboratory NASA Goddard Space Flight Center Planetary Environments Laboratory NASA Goddard Space Flight Center

Over the past decade, the study of extrasolar planets has evolved rapidly from plain detection and identification to comprehensive categorization and characterization of exoplanet systems and their atmospheres. Atmospheric retrieval, the inverse modeling technique used to determine an exoplanetary atmosphere's temperature structure and composition from an observed spectrum, is both time-consuming and compute-intensive, requiring complex algorithms that compare thousands to millions of atmospheric models to the observational data to find the most probable values and associated uncertainties for each model parameter [12]. For rocky, terrestrial planets, the retrieved atmospheric composition can give insight into the surface fluxes of gaseous species necessary to maintain the stability of that atmosphere, which may in turn provide insight into the geological and/or biological processes active on the planet [16]. These atmospheres contain many molecules, some of them biosignatures, spectral fingerprints indicative of biological activity, which will become observable with the next generation of telescopes [5]. Runtimes of traditional retrieval models scale with the number of model parameters, so as more molecular species are considered, runtimes can become prohibitively long. Recent advances in machine learning (ml) and computer vision [11, 8] offer new ways to reduce the time to perform a retrieval by orders of magnitude [13, 23], given a sufficient data set to train with. Here we present an ml-based retrieval framework called Intelligent exoplaNet Atmospheric RetrievAl (INARA) that consists of a Bayesian deep learning model for retrieval and a data set of 3,000,000 synthetic rocky exoplanetary spectra generated using the NASA Planetary Spectrum Generator (PSG) [20]. Our work represents the first ml retrieval model for rocky, terrestrial exoplanets and the first synthetic data set of terrestrial spectra generated at this *** Codes 85A20, 68T05 Copyright © 2018, Th

关键词： Extrasolar planets

Distributed hybrid control strategy for multiple wind farms under symmetrical and asymmetrical faults

学校读者我要写书评

暂无评论

Distributed hybrid control strategy for multiple wind farms ...

International Conference on Energy Conservation and Efficiency (ICECE)

作者： N. Shaukat B. Khan S. M. Ali Usman Munawar Z. Ullah Electrical Engineering Department COMSATS Institute of Information Technology Abbottabad Pakistan AI Khwarizmi institute of Computer Science University of Engineering and Technology Lahore

ISBN: (纸本)9781538636077

The research study in this paper develop an idea of Hybrid Control Approach (HCA) for electric grid interfaced Multiple Wind Farms (MWFs). The Doubly Fed Induction Generator (DFIG) based MWFs are considered for documented study in this paper. The main attention and focus were drawn towards Rotor Side Converter(RSC) Control. A case study of 27MW grid tied MWFs under symmetrical and asymmetrical faults is carried out in MATLAB/Simulink. In order to validate the effectiveness of the proposed cascaded control strategy, simulation results were compared with PI controller. We effectively reduce rotor side over currents with proposed control approach. The simulation results for electromagnetic torque, further demonstrated enhanced overall performance of the MWFs with proposed control scheme.

关键词： Rotors Stator windings Circuit faults Reactive power Simulation

Underwater multi-robot convoying using visual tracking by detection

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Shkurti, Florian Chang, Wei-Di Henderson, Peter Islam, Md Jahidul Higuera, Juan Camilo Gamboa Li, Jimmy Manderson, Travis Xu, Anqi Dudek, Gregory Sattar, Junaed Centre for Intelligent Machines School of Computer Science McGill University Interactive Robotics and Vision Laboratory Department of Computer Science and Engineering University of Minnesota- Twin Cities Element AI

We present a robust multi-robot convoying approach that relies on visual detection of the leading agent, thus enabling target following in unstructured 3-D environments. Our method is based on the idea of tracking-by-detection, which interleaves efficient model-based object detection with temporal filtering of image-based bounding box estimation. This approach has the important advantage of mitigating tracking drift (i.e. drifting away from the target object), which is a common symptom of model-free trackers and is detrimental to sustained convoying in practice. To illustrate our solution, we collected extensive footage of an underwater robot in ocean settings, and hand-annotated its location in each frame. Based on this dataset, we present an empirical comparison of multiple tracker variants, including the use of several convolutional neural networks, both with and without recurrent connections, as well as frequency-based model-free trackers. We also demonstrate the practicality of this tracking-by-detection strategy in real-world scenarios by successfully controlling a legged underwater robot in five degrees of freedom to follow another robot’s independent motion. Copyright © 2017, The Authors. All rights reserved.

关键词： Multipurpose robots

Recognizing Multi-talker Speech with Permutation Invariant Training

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yu, Dong Chang, Xuankai Qian, Yanmin Tencent AI Lab Seattle United States Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

In this paper, we propose a novel technique for direct recognition of multiple speech streams given the single channel of mixed speech, without first separating them. Our technique is based on permutation invariant training (PIT) for automatic speech recognition (ASR). In PIT-ASR, we compute the average cross entropy (CE) over all frames in the whole utterance for each possible output-target assignment, pick the one with the minimum CE, and optimize for that assignment. PIT-ASR forces all the frames of the same speaker to be aligned with the same output layer. This strategy elegantly solves the label permutation problem and speaker tracing problem in one shot. Our experiments on artificially mixed AMI data showed that the proposed approach is very promising. Copyright © 2017, The Authors. All rights reserved.

关键词： Speech recognition